{"id":"https://openalex.org/W3211715627","doi":"https://doi.org/10.1109/dac18074.2021.9586299","title":"An Energy-Efficient Low-Latency 3D-CNN Accelerator Leveraging Temporal Locality, Full Zero-Skipping, and Hierarchical Load Balance","display_name":"An Energy-Efficient Low-Latency 3D-CNN Accelerator Leveraging Temporal Locality, Full Zero-Skipping, and Hierarchical Load Balance","publication_year":2021,"publication_date":"2021-11-08","ids":{"openalex":"https://openalex.org/W3211715627","doi":"https://doi.org/10.1109/dac18074.2021.9586299","mag":"3211715627"},"language":"en","primary_location":{"id":"doi:10.1109/dac18074.2021.9586299","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac18074.2021.9586299","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 58th ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088778898","display_name":"Changchun Zhou","orcid":"https://orcid.org/0009-0005-3968-5048"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changchun Zhou","raw_affiliation_strings":["VLSI Lab, School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VLSI Lab, School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343894","display_name":"Min Liu","orcid":"https://orcid.org/0000-0002-3785-6932"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Liu","raw_affiliation_strings":["VLSI Lab, School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VLSI Lab, School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022639653","display_name":"Siyuan Qiu","orcid":"https://orcid.org/0000-0003-3631-1313"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Qiu","raw_affiliation_strings":["VLSI Lab, School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VLSI Lab, School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101585745","display_name":"Yifan He","orcid":"https://orcid.org/0000-0002-9171-3502"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifan He","raw_affiliation_strings":["Reconova Technologies Co., Ltd., Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reconova Technologies Co., Ltd., Xiamen, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042636120","display_name":"Hailong Jiao","orcid":"https://orcid.org/0000-0002-2815-6168"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hailong Jiao","raw_affiliation_strings":["VLSI Lab, School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VLSI Lab, School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"241","last_page":"246"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.8294952511787415},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8294534087181091},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6321351528167725},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5858653783798218},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.555139422416687},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5435270667076111},{"id":"https://openalex.org/keywords/frame-rate","display_name":"Frame rate","score":0.5088698863983154},{"id":"https://openalex.org/keywords/cmos","display_name":"CMOS","score":0.49015602469444275},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.4777059555053711},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.43928664922714233},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3490210175514221},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.31932532787323},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23259568214416504},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.1484050452709198},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10531532764434814}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.8294952511787415},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8294534087181091},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6321351528167725},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5858653783798218},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.555139422416687},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5435270667076111},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.5088698863983154},{"id":"https://openalex.org/C46362747","wikidata":"https://www.wikidata.org/wiki/Q173431","display_name":"CMOS","level":2,"score":0.49015602469444275},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.4777059555053711},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.43928664922714233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3490210175514221},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.31932532787323},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23259568214416504},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.1484050452709198},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10531532764434814},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dac18074.2021.9586299","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac18074.2021.9586299","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 58th ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.6600000262260437,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W1522734439","https://openalex.org/W1686810756","https://openalex.org/W1983364832","https://openalex.org/W2016053056","https://openalex.org/W2044535169","https://openalex.org/W2163605009","https://openalex.org/W2289252105","https://openalex.org/W2289615953","https://openalex.org/W2516141709","https://openalex.org/W2604319603","https://openalex.org/W2625457103","https://openalex.org/W2794141774","https://openalex.org/W2809254203","https://openalex.org/W2903486342","https://openalex.org/W2912834795","https://openalex.org/W2950861940","https://openalex.org/W2987129023","https://openalex.org/W3024621361","https://openalex.org/W3026054707","https://openalex.org/W4236868170","https://openalex.org/W6637373629","https://openalex.org/W6684191040","https://openalex.org/W6696711501"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W4391547476","https://openalex.org/W2004851054"],"abstract_inverted_index":{"Three-dimensional":[0],"convolutional":[1,86],"neural":[2],"network":[3],"(3D-CNN)":[4],"has":[5],"demonstrated":[6],"outstanding":[7],"classification":[8],"performance":[9],"in":[10,110,117],"video":[11],"recognition":[12],"compared":[13,122],"to":[14,67,74,97,119,123],"two-dimensional":[15],"CNN":[16],"(2D-CNN),":[17],"since":[18],"3D-CNN":[19,39,54,106],"not":[20],"only":[21],"learns":[22,31],"the":[23,32,69,77,102,124,130],"spatial":[24],"features":[25,34],"of":[26,71,79,137],"each":[27],"frame,":[28],"but":[29],"also":[30,95],"temporal":[33],"across":[35],"all":[36],"frames.":[37],"However,":[38],"suffers":[40],"from":[41],"intensive":[42],"computation":[43],"and":[44,60,81,143],"data":[45],"movement.":[46],"To":[47],"solve":[48],"these":[49],"issues,":[50],"an":[51,134],"energy-efficient":[52],"low-latency":[53],"accelerator":[55,107,132],"is":[56,88,94,108],"proposed.":[57,89],"Temporal":[58],"locality":[59],"small":[61],"differential":[62],"value":[63],"dropout":[64],"are":[65],"used":[66],"increase":[68],"sparsity":[70,78],"activation.":[72],"Furthermore,":[73],"fully":[75],"utilize":[76],"weight":[80],"activation,":[82],"a":[83,105,111],"full":[84],"zero-skipping":[85],"microarchitecture":[87],"A":[90],"hierarchical":[91],"load-balancing":[92],"scheme":[93],"introduced":[96],"improve":[98],"resource":[99],"utilization.":[100],"With":[101],"proposed":[103,131],"techniques,":[104],"designed":[109],"55-nm":[112],"low-power":[113],"CMOS":[114],"technology,":[115],"bringing":[116],"up":[118],"9.89\u00d7":[120],"speedup":[121],"baseline":[125],"implementation.":[126],"Benchmarked":[127],"with":[128],"C3D,":[129],"achieves":[133],"energy":[135],"efficiency":[136],"4.66":[138],"TOPS/W":[139],"at":[140],"100":[141],"MHz":[142],"1.08":[144],"V":[145],"supply":[146],"voltage.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}